E-Buyur Market: Fruit and Vegetable Quality Detection Platform Using On-Device Hybrid Artificial Intelligence Method to Reduce Food Loss in MSMEs
DOI:
https://doi.org/10.15294/edukom.v13i1.41313Keywords:
Food Loss and Waste, Marketplace, Mobile Net, MSME, Tensor Flow LiteAbstract
Indonesia produces large volumes of fruits and vegetables yet faces high food loss and waste (FLW), with studies estimating 23-48 million tons of food waste annually. Observations in Grobogan Regency show traders discarding around 30-40% of daily stock, often produce that is edible but visually imperfect (grade B/C). This study designs and evaluates E-Buyur Market, a digital marketplace embedding an on-device hybrid AI pipeline to automatically signal fruit-vegetable quality. The system combines a YOLO-TFLite commodity detector with a multitask MobileNetV3-Small TFLite grader to predict type, edibility, and a quality score derived from freshness probability. The model was trained on approximately 115,000 images compiled from publicly available Kaggle fruit-vegetable repositories, processed using data augmentation and post-training quantization for TensorFlow Lite deployment; a separate small set of real seller-captured photos was used to qualitatively test the deployed model under real usage conditions. On a held-out test set, the model achieves a type-classification accuracy of 0.91, freshness ROC-AUC of 0.94, PR-AUC of 0.92, and inference latency of tens of milliseconds on mid-range phones. Based on the system's design and signaling-theory rationale, on-device hybrid AI is expected to improve sell-through, reduce shrinkage, and shorten time-to-list for MSME sellers; empirical validation of these business-level outcomes through a live field trial remains future work.
References
Badan Pangan Nasional. (2023). Gerakan Selamatkan Pangan untuk Pencegahan Food Waste. Retrieved from https://badanpangan.go.id/blog/post/nfa-perkuat-gerakan-selamatkan-pangan-untuk-pencegahan-food-waste
Bochkovskiy, A., Wang, C-Y., & Liao, H-Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
Chen, Y., Zheng, B., Zhang, Z., Wang, Q., Shen, C., & Zhang, Q. (2020). Deep learning on mobile and embedded devices: State-of-the-art, challenges, and future directions. ACM Computing Surveys, 53(4), Article 84.
David, R., Duke, J., Jain, A., et al. (2021). TensorFlow Lite Micro: Embedded machine learning on TinyML systems. In Proceedings of Machine Learning and Systems 2021 (MLSys).
Fu, Y., Nguyen, M., & Yan, W-Q. (2022). Grading methods for fruit freshness based on deep learning. SN Computer Science, 3, 264.
Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021). YOLOX: Exceeding YOLO series in 2021. arXiv preprint arXiv:2107.08430.
Hasibuan, E. S. D., & Hendrik, B. (2025). Perbandingan Metode Deep Learning dalam Deteksi Kekerasan Fisik Berbasis Video: Studi Literatur pada CNN, RNN/LSTM, 3D-CNN, dan YOLO. Journal of Education Research, 6(4), 980-988.
Hayat, A., et al. (2024). FruitVision: A deep learning based automatic fruit grading system. Open Agriculture, 9(1), Article 20220276.
Hendrawan, S. A., Chatra, A., Iman, N., Hidayatullah, S., & Suprayitno, D. (2024). Digital transformation in MSMEs: Challenges and opportunities in technology management. Jurnal Informasi dan Teknologi, 6(2), 141-149.
Howard, A., Sandler, M., Chu, G., et al. (2019). Searching for MobileNetV3. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV 2019) (pp. 1314-1324).
Kementerian PPN/Bappenas. (2021). Kajian Food Loss and Waste di Indonesia 2000-2019. Jakarta: Kementerian PPN/Bappenas.
Mirwansyah, D., & Wibowo, A. (2022). Fruit image classification using deep learning algorithm: Systematic literature review (SLR). Multica Science and Technology (MST) Journal, 2(2), 120-123.
Rajmohan, S., Mendem, M. T., Vanam, S. S., & Thalapally, P. K. (2023). Online grading of fruits using deep learning models and computer vision. In Proceedings of the 4th International Conference on Information Management & Machine Intelligence (ICIMMI 2022) (pp. 1-8). ACM.
Rashidi, M. (2022). Application of TensorFlow Lite on embedded devices: A hands-on practice of TensorFlow model conversion to TensorFlow Lite model and its deployment on smartphone to compare model's performance (Bachelor thesis). Mid Sweden University.
TensorFlow Lite. (2023). TensorFlow Lite documentation. Retrieved from https://www.tensorflow.org/lite
United Nations. (2015). Transforming Our World: The 2030 Agenda for Sustainable Development. New York: United Nations.
United Nations. (2024). Goal 12: Ensure Sustainable Consumption and Production Patterns. Retrieved from https://www.un.org/sustainabledevelopment/sustainable-consumption-production/
Wang, C-Y., Bochkovskiy, A., & Liao, H-Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2023).
Yuan, Y., & Chen, J. (2024). Vegetable and fruit freshness detection based on deep features and principal component analysis. Current Research in Food Science, 8, 100656.
Zárate, V., & Cáceres Hernández, R. (2024). Simplified deep learning for accessible fruit quality assessment in small agricultural operations. Applied Sciences, 14(18), 8243.
Zhang, G., Chen, J., Li, W., & Huang, H. (2020). Risk assessment and monitoring of green logistics for fresh agricultural products in e-commerce environment. Sustainability, 12(18), 756
